© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1274
    Prev
    Next
    INDEX
    Explanations

    words related to industrial chemistry, especially the creation of gas

    oai_token-act-pair · gemini-2.0-flash

    gas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gas
    -2.61
     Gas
    -2.31
    Gas
    -2.28
    gas
    -2.03
     GAS
    -1.85
    GAS
    -1.62
     gases
    -1.52
     gás
    -1.42
    ガス
    -1.35
     газо
    -1.21
    POSITIVE LOGITS
     الاطلاع
    0.63
    sidemargin
    0.57
    Gruss
    0.56
    PropertyChanging
    0.52
     BorderRadius
    0.51
    љено
    0.50
     preferências
    0.50
     affirmative
    0.49
    Diweddarwch
    0.49
    IsSet
    0.48
    Activations Density 11.932%

    No Known Activations